Gmail MCP Server (SfdcAnnu/Gmail-MCP-Server) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 11 tools. No publisher has claimed this listing.
Enables interaction with Gmail through 11 tools for email management, including reading, sending, replying, searching, and labeling, with OAuth 2.1 authentication and support for various MCP clients.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
SfdcAnnu
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
listEmailsLists Gmail messages, newest first. USE THIS FIRST to discover message ids — every other mail tool takes the ids this returns. Returns metadata + a short snippet only. Call readEmail for the full body. LABELS (Gmail folders): INBOX (default), SENT, DRAFT, TRASH, SPAM, STARRED, IMPORTANT — or a lab…
readEmailReads one Gmail message in full — headers, complete body (text + HTML), attachment list, and the threading headers needed for replies.
searchEmailsSearches all Gmail mail with Gmail's native query syntax. USE searchEmails INSTEAD OF listEmails WHEN: • Looking for a topic, order number, name, or phrase — not a specific label • You don't know which label holds the message QUERY SYNTAX (same as the Gmail search box): from:jane@acme.com to:me …
listLabelsLists all Gmail labels (Gmail's equivalent of folders) with unread/total counts. Use when the user references a custom label ('check my Invoices label') — pass the returned label id to listEmails/moveEmail.
getAttachmentsLists the attachments on a message (name, type, size). Does NOT download binary content — report the names/sizes to the user instead.
sendEmailSends a new email from the connected Gmail account. RULES: • Confirm recipients and content with the user before sending anything they did not explicitly dictate. • bodyType 'html' allows formatting (<b>, <p>, lists); 'text' sends plain text. • The message lands in the user's Sent label.
replyEmailReplies to an existing Gmail message in-thread. Confirm the reply text with the user before sending unless they dictated it. replyAll=true includes all original recipients in the reply.
createDraftCreates a Gmail draft WITHOUT sending it. The user reviews and sends from Gmail themselves. Prefer this over sendEmail when the user says 'draft', 'prepare', or hasn't confirmed sending.
moveEmailMoves a Gmail message: archive it (remove from INBOX), trash it, or apply a different label. Gmail 'folders' are labels — get ids from listLabels.
markEmailMarks a Gmail message read/unread and/or stars it.
getProfileReturns the connected Gmail account (email address, total messages). Use to confirm which account is connected before sending on the user's behalf.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
BASE_URL/auth/callback (PATH B standalone)GOOGLE_CLIENT_IDcp .env.example .env # fill in / GOOGLE_CLIENT_SECRET / BASE_URLGOOGLE_CLIENT_SECRETcp .env.example .env # fill in GOOGLE_CLIENT_ID / / BASE_URLGOOGLE_REDIRECT_URIGOOGLE_CLIENT_SECRET, =<BASE_URL>/auth/callbackPORTTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
11/11 tools missing one or more hints — listEmails (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); readEmail (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); searchEmails (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
9/11 tool handlers declare input schemas (82%)
Declare an inputSchema with zod/joi/yup on every tool definition.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 17 high severity in production deps — @modelcontextprotocol/sdk@1.10.2 (high), @modelcontextprotocol/sdk@1.10.2 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/sfdcannu/gmail-mcp-server)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check